AUTHOR=Liao Kai , Wu Huanhua , Jiang Yuanfang , Dong Chenchen , Zhou Hailing , Wu Biao , Tang Yongjin , Gong Jian , Ye Weijian , Hu Youzhu , Guo Qiang , Xu Hao 

TITLE=Machine learning techniques based on 18F-FDG PET radiomics features of temporal regions for the classification of temporal lobe epilepsy patients from healthy controls

JOURNAL=Frontiers in Neurology

VOLUME=Volume 15 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/neurology/articles/10.3389/fneur.2024.1377538

DOI=10.3389/fneur.2024.1377538

ISSN=1664-2295

ABSTRACT=Background
To investigate the clinical application of 18F-FDG PET radiomics features for temporal lobe epilepsy and create PET radiomics-based machine learning models for differentiating TLE patients from healthy controls.
Methods
A total of 347 subjects that underwent 18F-FDG PET scans from March 2014 to January 2020 (234 TLE patients: 25.50 ± 8.89 years, 141 male and 93 female; and 113 controls: 27.59 ± 6.94 years, 48 male and 65 female) were allocated to training (n = 248) and test (n = 99) sets. All 3D PET images were registered to the Montreal Neurological Institute template. PyRadiomics was used to extract radiomics features from the temporal regions segmented according to the AAL atlas. The least absolute shrinkage and selection operator (LASSO) and Boruta algorithms were applied to select the radiomic features significantly associated with TLE. Eleven machine-learning algorithms were used to establish models and to select the best model in the training set.
Results
The final radiomics features （n = 7）used for model training were selected by the combinations of the least LASSO and the Boruta algorithm with cross-validation. All data were randomly divided into a training set (n = 248) and a testing set (n = 99). Among eleven machine-learning algorithms, the logistic regression (AUC 0.984, F1-Score 0.959) performed the best in the training set. Then we deployed the corresponding online website version (https://wane199.shinyapps.io/TLE_DynNom/), showing the details of the LR model for convenience. The AUCs of the tuned logistic regression model in the training and test sets were 0.981 and 0.957. And the calibration curves demonstrated satisfactory alignment (visually assessed) for identifying the TLE patients.
Conclusions
The radiomics model from temporal regions can be a potential method for distinguishing TLE. Machine learning-based diagnosis of TLE from preoperative FDG PET images could serve as a useful preoperative diagnostic tool.